@PerryLink

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

MCP management console for the official DeepSeek Harness MCP client: /mcp command with health diagnostics and pipeline trial calls, a Settings MCP tab with server CRUD (approval-gated writes, automatic backups) and a tool trial console over the official tool pipeline (Apache-2.0, dsh-plugin).

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

Claude Code /rewind for DeepSeek Harness — git-first workspace snapshots before every mutation, turn-boundary session forks, one-shot /rewind restore. A dsh-plugin capability seam.

Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace recall - and sliding-context awareness (compaction summaries in recall/search, compaction notice with one-click /compact fill).

Four-source migration wizard for DeepSeek Harness: move Claude Code, Codex, OpenCode and Hermes sessions, memories, skills, instructions and slash commands into DSH (/move wizard + resumable sessions, approval-gated, idempotent).

LSP action surface for DeepSeek Harness: diagnostics, formatting, completion, code actions, symbols, signature help, inlay hints, and rename tools over language servers

Interactive long-session background agents for DeepSeek Harness: start a durable continuable child agent, watch its progress in the Web UI sidebar, message it any time, and interrupt it - all through the official subagent seam.

Double-check before you ship: grill the requirements, test the implementation, prove the delivery. An engineering-discipline bundle for DeepSeek Harness.

Installable DSH bundle: the dsh-plugin-guide plugin-development knowledge base as an on-demand agent skill. Official docs archive (EN/ZH), Cordis primer, 114-repo community archive, 1654 archived Discussions, 20+ battle-tested pitfalls.

Official-grade GitHub CI for DeepSeek Harness: composite action.yml, PR review bot with idempotent inline comments and a status-check gate, plus PR/issues tools with every write gated by human approval (Apache-2.0, dsh-plugin).

Claude Code outputStyles for DeepSeek Harness - session-scoped, durable, runtime-switchable model output styles (/style command, output_style storage domain, systemPrompt injection)

Pin sessions and workspaces to the top of the DeepSeek Harness sidebar with per-pin row colors - a dual-face (host + client) dsh plugin.

Security-audit skill pack + plugin_vet supply-chain gate for DeepSeek Harness (dsh): 8 bilingual agent skills (secret scan, dependency audit, supply-chain review, prompt-injection review, audit orchestration, threat modeling, vuln intel, incident response) plus the plugin_vet automated pre-install scanner. Apache-2.0.

Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, budget caps with threshold alerts and over-limit policies, carbon footprint estimation, per-model latency benchmarks, a Settings budget tab, and the /budget command

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

Cross-device DeepSeek Harness session sync: a dedicated git mirror with append-only keep-both conflict resolution (fork files, never silently overwritten), /sync command and sync_* tools

Cross-platform native desktop control for DeepSeek Harness (Windows first): screen_shot, screen_read, click/type/scroll/key, app_list/app_launch - approval-gated, never stealing foreground focus

Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanitized audit events

Local document knowledge base for DeepSeek Harness: library_add/remove/list, hybrid semantic+keyword library_search with diversity re-ranking, relevance filtering and lost-in-the-middle avoidance, citation-aware injection, library_cite_check and library_diagnose 鈥?SQLite-backed index via the storage domain, local embedding, zero model downloads

Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint) with health-aware fallback, durable workspace attachments, per-session quota accounting, and a Plugins settings panel

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, sanitized prompt/completion capture, async batching, bounded offline buffering, retry with backoff

Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.

Isolated install-and-smoke test drives for DeepSeek Harness plugins: installs a repo or npm package into a throwaway DSH_HOME profile, verifies the bundle patch layer and boot logs, records a structured pass/fail result matrix (JSON/Markdown) for scoring pipelines, and quarantines every temp directory it owns

Multi-dimensional quality scoring for DeepSeek Harness plugins: scores one repo or npm package across install success (consuming dsh-test-drive results), maintenance activity, documentation completeness, security scan, and protocol compliance ??every conclusion backed by real CLI evidence with audit timestamps ??and pr

Read-only performance diagnostics for DeepSeek Harness: session load (open/restore) timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate ??surfaced via the /fast command and the fast_report tool, persisted as reconstructable

Vendor parameter translation and deterministic JSON repair for DeepSeek Harness: /translate maps temperature/top_p/max_tokens/stop/system across 11 vendors, and the post-execute repair layer (plus fix_json) fixes broken JSON tool output without ever fabricating data

PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders before they reach the model, restore them at the display layer, keep the restore table only in memory and a controlled storage domain, never log plaintext, and expose /mask and the mask_test tool